A Review of Generative Design Using Machine Learning for Additive Manufacturing
This review explores how generative design is combined with machine learning (ML) to achieve additive manufacturing (AM) and its societal transformative effect. Generative design uses complex algorithms to automate the process of designing best-fit designs, mass customization, and customization to s...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Publishing House of the Rzeszow University of Technology
2024-10-01
|
| Series: | Advances in Mechanical and Materials Engineering |
| Subjects: | |
| Online Access: | https://journals.prz.edu.pl/amme/article/view/1791 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This review explores how generative design is combined with machine learning (ML) to achieve additive manufacturing (AM) and its societal transformative effect. Generative design uses complex algorithms to automate the process of designing best-fit designs, mass customization, and customization to suit specific customer requirements with high efficiency and quality. The scalability and predictability of artificial intelligence (AI) models make handling huge data easy and enable scale-up of production without compromising quality. This paper also focuses on how generative design can help accelerate innovation and product creation because it empowers designers to play in a wider space of design and provide solutions that cannot be reached with traditional techniques. AI integration with existing production processes is also vital to real-time manufacturing optimization—further increasing overall operational effectiveness. Additionally, the emergence of sophisticated predictive models like gradient boosting regression shows how ML can enable better accuracy and robustness of 3D printing operations to achieve quality standards of the outputs. This paper ends with what generative design and ML hold for the future of AM and how designing continues to be improved and modified to match changing industry requirements. |
|---|---|
| ISSN: | 2956-4794 |